Article Per Year (5 Year)
p-Index From 2021 - 2026
3.354
P-Index
This Author published in this journals
All Journal Techno.Com: Jurnal Teknologi Informasi MATICS : Jurnal Ilmu Komputer dan Teknologi Informasi (Journal of Computer Science and Information Technology) Jurnal EECCIS POSITIF ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika JURNAL NASIONAL TEKNIK ELEKTRO Jurnal Teknologi dan Sistem Komputer Jurnal Pilar Nusa Mandiri Network Engineering Research Operation [NERO] Pendas : Jurnah Ilmiah Pendidikan Dasar JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Jurnal RESISTOR (Rekayasa Sistem Komputer) Jurnal Intake : Jurnal Penelitian Ilmu Teknik dan Terapan G-Tech : Jurnal Teknologi Terapan Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Jurnal Pengabdian Masyarakat Asia Jurnal Teknik Informatika (JUTIF) Proceeding of The International Conference on Economics and Business Jurnal Seni dan Reka Rancang: Jurnal Ilmiah Magister Desain Jurnal INFOTEL NERO (Networking Engineering Research Operation) Teknomatika: Jurnal Informatika dan Komputer Jurnal ilmiah teknologi informasi Asia
Fransiska Sisilia Mukti
Program Studi Teknik Informatika, Fakultas Teknologi Dan Desain, Institut Teknologi Dan Bisnis Asia Malang
Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Energy Engineering Mechanical Engineering Other

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Optimasi Teknologi WAV2Vec 2.0 menggunakan Spectral Masking untuk meningkatkan Kualitas Transkripsi Teks Video bagi Tuna Rungu NOERCHOLIS, ACHMAD; DWIANDINI, TITANIA; MUKTI, FRANSISKA SISILIA
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 12, No 4: Published October 2024
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v12i4.877

Abstract

ABSTRAKTeknologi Automatic Speech Recognition (ASR) telah berkembang pesat sebagai alat untuk meningkatkan aksesibilitas informasi bagi penyandang tuna rungu, terutama melalui video. WAV2Vec 2.0, salah satu teknologi ASR unggulan, efektif dalam transkripsi teks, namun kinerjanya menurun saat menghadapi noise. Penelitian ini bertujuan mengoptimalkan WAV2Vec 2.0 dengan menerapkan Spectral Masking untuk mengurangi noise tanpa mengorbankan kejelasan sinyal utama. Evaluasi dilakukan pada tiga jenis video: podcast, video dengan background noise, dan video dengan background music. Hasil menunjukkan penurunan Word Error Rate (WER) yang signifikan, sebesar 78.06% pada podcast dan 53.85% pada video dengan background noise. Hasil penelitian menunjukkan bahwa Spectral Masking efektif dalam meningkatkan akurasi transkripsi, menawarkan solusi inovatif untuk aksesibilitas tuna rungu dalam kondisi audio yang kompleks.Kata kunci: noise reduction, spectral masking, tuna rungu, WAV2Vec 2.0 ABSTRACTAutomatic Speech Recognition (ASR) technology has rapidly evolved as a tool to enhance information accessibility for the hearing impaired, particularly through video content. WAV2Vec 2.0, a leading ASR technology, is effective in text transcription, but its performance degrades in the presence of noise. This study aims to optimize WAV2Vec 2.0 by applying Spectral Masking to reduce noise without compromising the clarity of the main signal. The evaluation was conducted on three types of videos: podcasts, videos with background noise, and videos with background music. The results show a significant reduction in Word Error Rate (WER), with a 78.06% decrease in podcasts and a 53.85% decrease in videos with background noise. These findings demonstrate that Spectral Masking effectively enhances transcription accuracy, offering an innovative solution for improving accessibility for the hearing impaired in complex audio conditions.Keywords: noise reduction, spectral masking, tuna rungu, WAV2Vec 2.0
MQTT Broker Optimization: Comparative Analysis of Round Robin and Least Response Time Arifin, Samsul; Nugraha, Alfian Wahyu; Mukti, Fransiska Sisilia; Jatmika, Sunu
JURNAL NASIONAL TEKNIK ELEKTRO Vol 13, No 3: November 2024
Publisher : Jurusan Teknik Elektro Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jnte.v13n3.1260.2024

Abstract

Optimizing MQTT broker performance is crucial for maintaining efficient message routing in IoT systems, especially under varying workloads and QoS levels. This study compares the Round Robin (RR) and Least Response Time (LRT) algorithms to evaluate their performance across QoS levels 0, 1, and 2 and client loads ranging from 500 to 2,500 clients. Using Apache JMeter, key metrics such as CPU usage, throughput, delay, jitter, and response time were assessed. LRT was found to excel in enhancing response time and reducing delay, particularly under high client loads and in applications requiring minimal latency. However, this comes at the cost of higher CPU usage under heavy loads. In contrast, RR demonstrated optimal performance in maintaining balanced CPU utilization and predictable performance, though with slightly higher response times. Both algorithms demonstrated linear scalability in throughput, confirming their ability to handle increasing workloads without bottlenecks. These findings offer practical guidance for IoT developers: in latency-sensitive environments such as industrial automation, LRT is preferable due to its low-latency benefits, while RR is better suited for resource-constrained IoT systems like environmental monitoring, where stability and even load distribution are prioritized. The trade-offs identified provide valuable insights for selecting appropriate algorithms based on specific application requirements.
Peramalan Jumlah Kasus Covid 19 di Jawa Timur Menggunakan Metode Triple Eksponensial Smoothing Siti Nurul Afiyah; Nur Lailatul Aqromi; Fransiska Sisilia Mukti
Jurnal Ilmiah Teknologi Informasi Asia Vol 16 No 1 (2022): Volume 16 Nomor 1 (8)
Publisher : LP2M INSTITUT TEKNOLOGI DAN BISNIS ASIA MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32815/jitika.v16i1.694

Abstract

East Java is one of the areas that has many cases of covid 19, therefore the East Java provincial government must increase the number of cases of covid 19 in East Java, including by promoting the health protocol program 5. The pattern of data on cases of covid 19 in East Java shows fluctuating data patterns. Forecasting that can be used is the triple exponential smoothing method. From the test results obtained accuracy of 71.25%. It is hoped that the forecasting results can later be used as a reference for formulating East Java provincial government policies for the next period.
Analisis Penempatan Access Point Pada Jaringan Wireless LAN STMIK Asia Malang Menggunakan One Slope Model Mukti, Fransiska Sisilia; Sulistyo, Danang Arbian
Jurnal Ilmiah Teknologi Informasi Asia Vol 13 No 1 (2019): Volume 13 Nomor 1 (8)
Publisher : LP2M Institut Teknologi dan Bisnis ASIA Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini bertujuan untuk menganalisis penempatan access point (AP) pada jaringan WLAN STMIK Asia Malang, yang berdampak terhadap level daya atau kuat sinyal yang diterima oleh pengguna. Pendekatan pertama melalui site survey, dengan tujuan yakni mendapatkan informasi yang cukup mengenai jumlah dan penempatan AP yang saat ini diaplikasikan pada gedung kampus STMIK Asia Malang. Hasil dari walktest ini akan digunakan sebagai parameter untuk perhitungan teoritis menggunakan model propagasi One Slope Model (1SM). Berdasarkan perhitungan 1SM, didapatkan jarak optimal untuk penempatan AP tidak lebih dari 13 m pada propagasi LOS (rentang kuat sinyal -10dB sampai dengan -20dB, pada area koridor gedung) dan jarak 6 m pada propagasi NLOS (rentang kuat sinyal -40dB sampai dengan -50dB, pada area ruangan perkuliahan). Hasil analisis membuktikan bahwa keberadaan barrier mempengaruhi kekuatan sinyal yang diterima oleh user, sehingga penempatan perangkat WLAN, dalam hal ini AP perlu diperhatikan.
ROUTING OPTIMIZATION ON SOFTWARE DEFINED NETWORK ARCHITECTURE USING BREADTH FIRST SEARCH ALGORITHM Armanda, David; Mukti, Fransiska Sisilia; Sulistyo, Danang Arbian
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024 - SENIKO
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2000

Abstract

Software Defined Network (SDN) is a network modelling that separates the control plane and data plane. SDN is a new form of paradigm used for large-scale networks, one of which is for routing. Most types of routing used today use single-path routing. Single-path only uses one path as data transmission. This will result in reduced performance on the network which is often referred to as network congestion. In this test, the routing algorithm used is Breadth First Search (BFS) by modifying the path so that congestion on the network can be minimised. The BFS algorithm is implemented using Mininet emulator, Ryu Controller, and fat-tree topology. In the test, 20 scenarios were used with a bandwidth of 50 - 1000 Mbps within 15 seconds. Tests were conducted to measure the performance of the BFS algorithm, namely the path and QOS (Quality Of Service) parameters which include testing delay, packet loss, jitter, and throughput. The data obtained in testing using the conventional BFS algorithm is compared with the modified BFS algorithm data in the same test method. In path testing, the modified BFS algorithm is superior and in parameter testing, it is produced with a degraded percentage value in delay (65%), packet loss (99%), jitter (84%), and throughput has increased by (41%). So the modified BFS algorithm is superior due to the utilisation of path modification for routing optimisation which is more effective in handling network congestion.
INTEGRASI METODE PCQ DAN HTB UNTUK MENGOPTIMALKAN PENGGUNAAN BANDWIDTH INTERNET DI LINGKUNGAN SEKOLAH Mukti, Fransiska Sisilia; Latul Roza, Syahfadi
NERO (Networking Engineering Research Operation) Vol 8, No 1 (2023): Nero - 2023
Publisher : Jurusan Teknik Informatika Fakultas Teknik Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/nero.v8i1.19279

Abstract

Berlangganan kapasitas bandwidth yang besar tidak selalu memberikan jaminan bahwa layanan yang diberikan kepada pengguna akan maksimal. Tanpa adanya manajemen bandwidth yang tepat, maka pengguna dapat saja berebut internet dan terjadi sebuah ketimpangan bandwidth yang diterima. Pengelolaan bandwidth biasanya akan diimbangi dengan adanya pengelolaan user melalui konsep pemetaan tingkat prioritas user, dengan tujuan untuk mendapatkan hasil manajemen jaringan yang lebih baik. Untuk itu, penelitian ini secara khusus mengusulkan sebuah metode pengintegrasian skema manajemen jaringan dalam bentuk manajemen pengguna dan manajemen bandwidth. Manajemen pengguna dilakukan melalui pengklasifikasian pengguna berdasarkan tingkat kepentingannya masing-masing dengan menggunakan metode Hierarchical Token Bucket (HTB). Sementara manajemen bandwidth yang merata untuk seluruh pengguna diusulkan dengan mengintegrasikan konsep Per Connection Queue (PCQ) yang bersifat dinamis, tanpa membebani router. Hasil penelitian menunjukkan bahwa pengintegrasian metode PCQ-HTB memberikan sebuah alternatif baru dalam manajemen jaringan. Terjadi peningkatan nilai throughput yang dihasilkan mencapai 12,18 kali lipat, yang juga diimbangi dengan akses internet pengguna yang lebih merata.  Kata kunci: HTB, Internet Sekolah, Manajemen Bandwidth, Mikrotik, PCQ
Peningkatan Akurasi Deteksi Intrusi Jaringan dengan Model Hybrid Convolutional Neural Network dan Long Short-Term Memory Ficho Pranandasya Andrian Pratama; Danang Arbian Sulistyo; Fransiska Sisilia Mukti
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 10, No 2 (2025): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v10i2.895

Abstract

The evolving cyber threats demand more sophisticated and accurate intrusion detection systems (IDS). This research develops a hybrid CNN-LSTM model with comprehensive data preprocessing techniques to enhance network attack detection accuracy. The UNSW-NB15 dataset consisting of nine attack categories and 49 features was used as research data. The methodology begins with data preprocessing including data cleaning, categorical transformation using categorical codes, class balancing with upsampling, StandardScaler normalization, and 80:20 data splitting. The hybrid model architecture combines three CNN blocks for spatial feature extraction with two LSTM layers for modeling temporal dependencies. The model was compiled using Adam optimizer with 0.0005 learning rate and equipped with EarlyStopping, ReduceLROnPlateau, and ModelCheckpoint callbacks. Evaluation results show the CNN-LSTM model achieves 99% accuracy, precision, recall, and F1-score, significantly outperforming the standard CNN model which only reaches 96%. Learning curves demonstrate rapid convergence without overfitting indication. This research proves that the combination of CNN's spatial feature extraction capability and LSTM's temporal dependency modeling is highly effective for anomaly detection in complex sequential data such as network traffic.
IMPLEMENTASI SNORT INLINE MODE DAN ELK STACK UNTUK DETEKSI DAN MITIGASI SERANGAN PADA INFRASTRUKTUR LAYANAN DIGITAL PENDIDIKAN BERBASIS DOCKER Vian Maulana Fatah; Achmad Noercholis; Fransiska Sisilia Mukti
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 02 (2026): Volume 11 No. 02 Juni 2026 Press
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i02.54016

Abstract

The rapid development of digital education services has increased educational institutions' dependence on information technology infrastructure. Various cyber threats such as brute force attacks, port scanning, ping sweep, and denial-of-service attacks can disrupt service availability and interfere with academic and administrative activities. Therefore, an effective security mechanism is required to detect and mitigate cyberattacks in real time. This study aims to implement a Snort Inline Mode-based Intrusion Prevention System integrated with the ELK Stack (Elasticsearch, Logstash, Kibana) within a Docker-based digital education services infrastructure environment. The research employed an experimental method by developing a containerized architecture consisting of attacker, digital education service server, Snort IPS, Filebeat, Logstash, Elasticsearch, and Kibana containers. Active mitigation was implemented using Netfilter Queue (NFQUEUE), enabling Snort to inspect and block malicious traffic before reaching the target server. Four attack scenarios were tested, including SSH Brute Force, ICMP Ping Sweep, TCP Port Scan, and TCP SYN Flood. The results indicate that the system successfully detected and mitigated all attack scenarios with a mitigation success rate of 100% and response times below one second. Furthermore, ELK Stack integration provided centralized and real-time security monitoring through Kibana dashboards, facilitating threat analysis and security management. The findings demonstrate that the combination of Snort Inline Mode and ELK Stack in a Docker environment can serve as an effective security solution to support the reliability, security, and availability of digital education services infrastructure
Implementasi Fail2Ban dan ELK Stack untuk Mitigasi Serangan Brute Force pada REST API Login E-Learning Berbasis Docker Widi laksono, Anggi; Achmad Noercholis; Fransiska Sisilia Mukti
Pendas : Jurnal Ilmiah Pendidikan Dasar Vol. 11 No. 03 (2026): Volume 11 Nomor 03, September 2026 Public
Publisher : Program Studi Pendidikan Guru Sekolah Dasar FKIP Universitas Pasundan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23969/jp.v11i03.55491

Abstract

The increasing adoption of digital learning systems (E-Learning) has raised the need for security mechanisms capable of protecting authentication services from cyber threats. One of the most common threats is a brute force attack, which exploits repeated login attempts using automated username and password combinations. This study aims to implement Fail2Ban and the ELK Stack to mitigate brute force attacks on a Docker-based E-Learning Login REST API. The research employed an experimental method by developing a containerized environment consisting of an E-Learning Login REST API, Fail2Ban, Filebeat, Logstash, Elasticsearch, Kibana, and attacker containers. Brute force attack simulations were conducted using Hydra against the authentication service. Data were collected from authentication logs, Fail2Ban logs, and security monitoring results visualized through Kibana dashboards. The results show that Fail2Ban successfully detected 180 failed login attempts originating from six attacker IP addresses and automatically blocked all attacker IPs, achieving a mitigation success rate of 100%. The average mitigation response time ranged from 0.314 to 0.443 seconds with a bantime of 500 seconds. Furthermore, the ELK Stack successfully provided real-time visualization of failed login activities, attacker IP addresses, and blocking actions. The findings indicate that the integration of Fail2Ban and the ELK Stack in a Docker environment is effective in improving the security of the E-Learning Login REST API against brute force attacks through centralized detection, mitigation, and security monitoring mechanisms.  
Co-Authors Achmad Basuki Achmad Noercholis Agus Purnomo Sidi Al Zahwa, Naviza Yulia Allin Junikhah Angga Eko Bayu Arieska Anjaningrum, Widiya Dewi Armanda, David Aziz, Aynan Salsabilah Danang Arbian Sulistyo Daniel Desma Mahendra Fadhli Almu’iini Ahda Faisal Edo Nugroho Farokhah, Lia Ficho Pranandasya Andrian Pratama Junikhah, Allin Kabelen, Nicholaus Wayong Latul Roza, Syahfadi Lorenzo, Juan Enrico Maria Theresia Indriastuti Nugraha, Alfian Wahyu Nur Lailatul Aqromi Nur Lailatul Aqromi Onny Setyawati Renny Wahyu Dewi Anjasari Roid Zuhdianto Samsul Arifin Setyorini Setyorini Setyorini Setyorini Siti Nurul Afiyah Siti Nurul Afiyah Sulistyo, Danang Arbian Sunu Jatmika Sunu Jatmika, Sunu Titania Dwi Andini Tria Aprilianto Tria Aprilianto, Tria Vian Maulana Fatah Widi laksono, Anggi Yogie Susdyastama Putra